Agent Development

This handles everything around building autonomous agents for Claude Code plugins. You'll use it when you need to understand agent frontmatter structure, write triggering descriptions with proper example blocks, design system prompts that actually work, or figure out when to use an agent versus a command. The source material is thorough on the mechanics: YAML frontmatter requirements, the description field format with context/user/assistant/commentary examples, model and color options, and tool restrictions. It also covers the system prompt template with responsibilities, process steps, and output formats. If you're building a plugin that needs subagents to handle complex workflows autonomously, this gives you the complete structure and validation rules. The AI-assisted generation method is particularly useful if you want Claude to scaffold agent configs from natural language descriptions.

skills.sh installs: 199
GitHub stars: 476
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add aiskillstore/marketplace --skill agent-development --agent claude-code

Installs into .claude/skills of the current project.

Files

Agent Development for Claude Code Plugins

Overview

Agents are autonomous subprocesses that handle complex, multi-step tasks independently. Understanding agent structure, triggering conditions, and system prompt design enables creating powerful autonomous capabilities.

Key concepts:

Agents are FOR autonomous work, commands are FOR user-initiated actions
Markdown file format with YAML frontmatter
Triggering via description field with examples
System prompt defines agent behavior
Model and color customization

Agent File Structure

Complete Format

---
name: agent-identifier
description: Use this agent when [triggering conditions]. Examples:

<example>
Context: [Situation description]
user: "[User request]"
assistant: "[How assistant should respond and use this agent]"
<commentary>
[Why this agent should be triggered]
</commentary>
</example>

<example>
[Additional example...]
</example>

model: inherit
color: blue
tools: ["Read", "Write", "Grep"]
---

You are [agent role description]...

**Your Core Responsibilities:**
1. [Responsibility 1]
2. [Responsibility 2]

**Analysis Process:**
[Step-by-step workflow]

SKILL.md on GitHub